© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 39267
    Prev
    Next
    INDEX
    Explanations

    Gold dust beautiful

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron strongly activates on long runs of consecutive dots (extended ellipses) used as section separators or truncation markers.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    end
    -2.50
    ch
    -2.34
    </b>
    -2.30
    er
    -2.25
    ka
    -2.13
    >
    -2.13
    \
    -2.11
    -2.00
    ki
    -2.00
    me
    -1.99
    POSITIVE LOGITS
    銪
    2.38
     superfí
    2.38
    ၟ
    2.34
     estímulo
    2.31
    からお
    2.31
     mohl
    2.27
    訁
    2.23
     Anſ
    2.17
    鹩
    2.17
     significativa
    2.16
    Activations Density 0.007%

    No Known Activations